GitHub repo leaderboard by stars, growth rate and activity.

• rtk-ai

  #1rtk-ai/rtk

  CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies

  Rust79,730 starslast pushed 2 days ago
• headroomlabs-ai

  #2headroomlabs-ai/headroom

  Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.

  Python71,128 starslast pushed 22 hours ago
• yvgude

  #3yvgude/lean-ctx

  LeanCTX — Context Intelligence for AI systems.

  Rust3,749 starslast pushed Yesterday
• jgravelle

  #4jgravelle/jcodemunch-mcp

  Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.

  Python2,677 starslast pushed Yesterday
• Paritok-official

  #5Paritok-official/paritok-4b-v1

  Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.

  Python1,451 starslast pushed 3 days ago
• activeing123

  #6activeing123/mcptoon

  MCP tool lists eat 71,929 tokens at 255 tools — more than half a 128K window before you ask anything. mcptoon reads the same tools back at 581 (-99.2%, measured). 128KB CLI, zero deps. Compute your own: activeing123.github.io/mcptoon/tools/token-tax

  HTML195 starslast pushed Yesterday
• crwdla

  #7crwdla/tokentab

  A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.

  Python77 starslast pushed 3 days ago

#	Repo	Language	Stars	30-day trend	Last updated
1	rtk-ai rtk-ai/rtk CLI proxy that reduces LLM token consumption by 60-90% on common dev commands. Single Rust binary, zero dependencies	Rust	79,730		last pushed 2 days ago
2	headroomlabs-ai headroomlabs-ai/headroom Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.	Python	71,128		last pushed 22 hours ago
3	yvgude yvgude/lean-ctx LeanCTX — Context Intelligence for AI systems.	Rust	3,749		last pushed Yesterday
4	jgravelle jgravelle/jcodemunch-mcp Cut AI token costs 95%+ on code exploration. The leading MCP server for precise, symbol-level GitHub code retrieval via tree-sitter AST. Works with Claude Code, Cursor & any MCP client. 313B+ tokens saved.	Python	2,677		last pushed Yesterday
5	Paritok-official Paritok-official/paritok-4b-v1 Non-destructive compression gateway for AI coding agents. Cuts token bills 25% on turn 1 to past 85% in long or saturated sessions, and fits ~3× more turns in the same context window. Powered by our open-source code-native 4B model. Drop-in for Claude Code, Cursor, Codex, OpenHands, and any BASE_URL agent.	Python	1,451		last pushed 3 days ago
6	activeing123 activeing123/mcptoon MCP tool lists eat 71,929 tokens at 255 tools — more than half a 128K window before you ask anything. mcptoon reads the same tools back at 581 (-99.2%, measured). 128KB CLI, zero deps. Compute your own: activeing123.github.io/mcptoon/tools/token-tax	HTML	195		last pushed Yesterday
7	crwdla crwdla/tokentab A CLI that reads Claude Code, Codex, and Gemini CLI session logs and works out how much they cost, by model, project, and day.	Python	77	—	last pushed 3 days ago

All · 11,474